summaryrefslogtreecommitdiffstats
path: root/python/fatcat_import.py
blob: fcb4941b3e6f9e87c91a792caa9f71e39b31a9d2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
#!/usr/bin/env python3

import os, sys, argparse
from fatcat_tools import authenticated_api
from fatcat_tools.importers import *


def run_crossref(args):
    fci = CrossrefImporter(args.api,
        args.issn_map_file,
        extid_map_file=args.extid_map_file,
        edit_batch_size=args.batch_size,
        bezerk_mode=args.bezerk_mode)
    if args.kafka_mode:
        KafkaJsonPusher(fci, args.kafka_hosts, args.kafka_env, "api-crossref", "fatcat-import").run()
    else:
        JsonLinePusher(fci, args.json_file).run()

def run_orcid(args):
    foi = OrcidImporter(args.api,
        edit_batch_size=args.batch_size)
    JsonLinePusher(foi, args.json_file).run()

def run_journal_metadata(args):
    fii = JournalMetadataImporter(args.api,
        edit_batch_size=args.batch_size)
    JsonLinePusher(fii, args.json_file).run()

def run_matched(args):
    fmi = MatchedImporter(args.api,
        bezerk_mode=args.bezerk_mode,
        edit_batch_size=args.batch_size)
    JsonLinePusher(fmi, args.json_file).run()

def run_grobid_metadata(args):
    fmi = GrobidMetadataImporter(args.api, edit_batch_size=args.batch_size, longtail_oa=args.longtail_oa)
    LinePusher(fmi, args.tsv_file).run()

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--debug',
        action='store_true',
        help="enable debugging interface")
    parser.add_argument('--host-url',
        default="http://localhost:9411/v0",
        help="connect to this host/port")
    parser.add_argument('--kafka-hosts',
        default="localhost:9092",
        help="list of Kafka brokers (host/port) to use")
    parser.add_argument('--kafka-env',
        default="qa",
        help="Kafka topic namespace to use (eg, prod, qa)")
    subparsers = parser.add_subparsers()

    sub_crossref = subparsers.add_parser('crossref')
    sub_crossref.set_defaults(
        func=run_crossref,
        auth_var="FATCAT_AUTH_WORKER_CROSSREF",
    )
    sub_crossref.add_argument('json_file',
        help="crossref JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_crossref.add_argument('issn_map_file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_crossref.add_argument('--extid-map-file',
        help="DOI-to-other-identifiers sqlite3 database",
        default=None, type=str)
    sub_crossref.add_argument('--batch-size',
        help="size of batch to send",
        default=50, type=int)
    sub_crossref.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_crossref.add_argument('--bezerk-mode',
        action='store_true',
        help="don't lookup existing DOIs, just insert (clobbers; only for fast bootstrap)")

    sub_orcid = subparsers.add_parser('orcid')
    sub_orcid.set_defaults(
        func=run_orcid,
        auth_var="FATCAT_AUTH_WORKER_ORCID"
    )
    sub_orcid.add_argument('json_file',
        help="orcid JSON file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_orcid.add_argument('--batch-size',
        help="size of batch to send",
        default=50, type=int)

    sub_journal_metadata = subparsers.add_parser('journal-metadata')
    sub_journal_metadata.set_defaults(
        func=run_journal_metadata,
        auth_var="FATCAT_AUTH_WORKER_JOURNAL_METADATA",
    )
    sub_journal_metadata.add_argument('json_file',
        help="Journal JSON metadata file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_journal_metadata.add_argument('--batch-size',
        help="size of batch to send",
        default=50, type=int)

    sub_matched = subparsers.add_parser('matched')
    sub_matched.set_defaults(
        func=run_matched,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_matched.add_argument('json_file',
        help="JSON file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_matched.add_argument('--batch-size',
        help="size of batch to send",
        default=50, type=int)
    sub_matched.add_argument('--bezerk-mode',
        action='store_true',
        help="don't lookup existing files, just insert (clobbers; only for fast bootstrap)")

    sub_grobid_metadata = subparsers.add_parser('grobid-metadata')
    sub_grobid_metadata.set_defaults(
        func=run_grobid_metadata,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_grobid_metadata.add_argument('tsv_file',
        help="TSV file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_grobid_metadata.add_argument('--group-size',
        help="editgroup group size to use",
        default=75, type=int)
    sub_matched.add_argument('--longtail-oa',
        action='store_true',
        help="if this is an import of longtail OA content (sets an 'extra' flag)")

    args = parser.parse_args()
    if not args.__dict__.get("func"):
        print("tell me what to do!")
        sys.exit(-1)

    args.api = authenticated_api(
        args.host_url,
        # token is an optional kwarg (can be empty string, None, etc)
        token=os.environ.get(args.auth_var))
    args.func(args)

if __name__ == '__main__':
    main()